© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15005
    Prev
    Next
    INDEX
    Explanations

    discourse markers and words denoting measurement

    oai_token-act-pair · gemini-2.0-flash

    Sides

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.82
    aarrggbb
    -0.64
     createState
    -0.63
     समीक्षक
    -0.59
    ConstraintMaker
    -0.58
    :][
    -0.54
    setContentView
    -0.54
     surla
    -0.53
     subsequence
    -0.51
     Wikimedijinoj
    -0.50
    POSITIVE LOGITS
     both
    3.14
    both
    2.88
    Both
    2.78
     Both
    2.78
     BOTH
    2.44
    BOTH
    2.44
     begge
    2.36
    Ambos
    2.30
     Beide
    2.28
     ambos
    2.27
    Activations Density 1.946%

    No Known Activations